Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    asking questions to clarify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    它的
    0.50
     dessen
    0.46
    让你
    0.39
     hepin
    0.39
     mio
    0.39
     mío
    0.38
     അയാള
    0.38
    Hepinize
    0.38
    Population
    0.37
    我说
    0.37
    POSITIVE LOGITS
     they
    0.61
     patients
    0.58
    患者
    0.57
     пациента
    0.56
     клиента
    0.54
    選手
    0.53
    他們
    0.49
     students
    0.48
     THEY
    0.47
     खिलाड़ी
    0.47
    Act Density 0.140%

    No Known Activations